Beyond Greedy Ranking: Slate Optimization via List-CVAE

Abstract

The conventional solution to the recommendation problem greedily ranks individual document candidates by prediction scores. However, this method fails to optimize the slate as a whole, and hence, often struggles to capture biases caused by the page layout and document interdepedencies. The slate recommendation problem aims to directly find the optimally ordered subset of documents (i.e. slates) that best serve users' interests. Solving this problem is hard due to the combinatorial explosion in all combinations of document candidates and their display positions on the page. Therefore we propose a paradigm shift from the traditional viewpoint of solving a ranking problem to a direct slate generation framework. In this paper, we introduce List Conditional Variational Auto-Encoders (List-CVAE), which learns the joint distribution of documents on the slate conditioned on user responses, and directly generates full slates. Experiments on simulated and real-world data show that List-CVAE outperforms popular comparable ranking methods consistently on various scales of documents corpora.

Cited by in corpus (8)

• RecSim: A Configurable Simulation Platform for Recommender Systems
• Context-Aware Learning to Rank with Self-Attention
• Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology
• AliExpress Learning-To-Rank: Maximizing Online Model Performance without Going Online
• Explore User Neighborhood for Real-time E-commerce Recommendation
• Exact-K Recommendation via Maximal Clique Optimization
• Off-Policy Evaluation of Slate Policies under Bayes Risk
• Conditional Sequential Slate Optimization